© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124030
    Prev
    Next
    INDEX
    Explanations

    completion, confirmation, status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bús
    -1.34
     cortos
    -1.30
     chaleco
    -1.23
     grises
    -1.20
     apto
    -1.19
     ouvert
    -1.19
     avenir
    -1.18
     emballage
    -1.17
     barcel
    -1.16
     ativ
    -1.16
    POSITIVE LOGITS
     for
    2.03
     and
    1.83
     to
    1.59
     때문
    1.47
    他们
    1.39
     няма
    1.29
     in
    1.26
    They
    1.23
    し
    1.17
     not
    1.16
    Activations Density 0.094%

    No Known Activations